Genetic algorithms and evolutionary programming hybrid strategy for structure and weight learning for multilayer feedforward neural networks

被引：17

作者：

Gao, FR ^{[1
]}

Li, MZ ^{[1
]}

Wang, FL ^{[1
]}

Wang, BG ^{[1
]}

Yue, PL ^{[1
]}

机构：

[1] Hong Kong Univ Sci & Technol, Dept Chem Engn, Kowloon, Peoples R China

来源：

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH | 1999年 / 38卷 / 11期

关键词：

D O I：

10.1021/ie990256h

中图分类号：

TQ [化学工业];

学科分类号：

0817 ;

摘要：

A hybrid strategy (GAs-EP) combining genetic algorithms (GAs) and evolutionary programming (EP) via a matrix group encoding is proposed to evolve a multilayer feedforward neural network, through simultaneously acquiring the network structure and weights. The strategy uses EP for evolving neural network and GAs for diversifying the individuals of the neural network population. This strategy inherits the strengths and suppresses the shortcomings of GAs and EP in their separate forms. The resulting strategy is simple and practical, and it has fast convergence. Its effectiveness has been demonstrated through its application to the polymer melt temperature prediction of injection molding.

引用

页码：4330 / 4336

页数：7

共 50 条

[31] A hybrid algorithm for weight and connectivity optimization in feedforward neural networks [J].

Pettersson, F ;

Saxén, H .

ARTIFICIAL NEURAL NETS AND GENETIC ALGORITHMS, PROCEEDINGS, 2003, :47-52

[32] OPTIMAL FILTERING ALGORITHMS FOR FAST LEARNING IN FEEDFORWARD NEURAL NETWORKS [J].

SHAH, S ;

PALMIERI, F ;

DATUM, M .

NEURAL NETWORKS, 1992, 5 (05) :779-787

[33] Combining Hybrid Genetic Algorithms and Feedforward Neural Networks for Pallet Loading in Real-World Applications [J].

Ancora, Gabriele ;

Palli, Gianluca ;

Melchiorri, Claudio .

HUMAN-FRIENDLY ROBOTICS 2021, 2022, :1-14

[34] A transformation strategy for implementing distributed, multilayer feedforward neural networks: Backpropagation transformation [J].

Rudolph, GL ;

Martinez, TR .

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF GRID COMPUTING AND ESCIENCE, 1997, 12 (06) :547-564

[35] Transformation strategy for implementing distributed, multilayer feedforward neural networks: Backpropagation transformation [J].

Rudolph, George L. ;

Martinez, Tony R. .

Future Generation Computer Systems, 1997, 12 (06) :547-564

[36] On the optimal structure design of multilayer feedforward neural networks for pattern recognition [J].

Chen, DQ ;

Burrell, P .

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2002, 16 (04) :375-398

[37] Research on multilayered feedforward neural networks-genetic-backpropagation algorithm & structure optimization strategy [J].

Chen, Rong ;

Xu, Yongmao ;

Lan, Hongsen .

Zidonghua Xuebao/Acta Automatica Sinica, 1997, 23 (01) :43-49

[38] A new modified hybrid learning algorithm for feedforward neural networks [J].

Han, F ;

Huang, DS ;

Cheung, YM ;

Huang, GB .

ADVANCES IN NEURAL NETWORKS - ISNN 2005, PT 1, PROCEEDINGS, 2005, 3496 :572-577

[39] ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks [J].

Shen, Jiangrong ;

Xu, Qi ;

Liu, Jian K. ;

Wang, Yueming ;

Pan, Gang ;

Tang, Huajin .

THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 1, 2023, :86-93

[40] STRUCTURE LEARNING OF BAYESIAN NETWORKS BASED ON HYBRID EVOLUTIONARY ALGORITHM WITH ELITE STRATEGY [J].

Shi, Jilong ;

Zhu, Yungang .

JOURNAL OF NONLINEAR AND CONVEX ANALYSIS, 2021, 22 (09) :1957-1970

← 1 2 3 4 5 →